refactor(exam): SKILL 中文化，增加用户确认阶段，默认子代理分批处理

2026-09-02 21:43:53 +08:00
parent 9e262abb23
commit 8759ba4659
8 changed files with 916 additions and 113 deletions
@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+"""Validate a question JSON file against the bundled schema.
+
+Usage:
+    python3 validate.py <json_file>
+    echo '<json>' | python3 validate.py -
+
+Exit codes: 0 = valid, 1 = errors found, 2 = usage error.
+"""
+import json
+import re
+import sys
+from pathlib import Path
+
+SCRIPT_DIR = Path(__file__).resolve().parent
+SCHEMA_PATH = SCRIPT_DIR.parent / "schema" / "question.schema.json"
+
+VALID_TYPES = [
+    "single_choice", "multiple_choice", "true_false",
+    "fill_blank", "short_answer", "code_reading", "scenario",
+]
+ID_RE = re.compile(r"^(sc|mc|tf|fb|sa|cr|sn)-\d{3}$")
+
+
+def load_json(path: str) -> dict:
+    if path == "-":
+        return json.load(sys.stdin)
+    with open(path, encoding="utf-8") as f:
+        return json.load(f)
+
+
+def validate(data: dict, schema: dict) -> list[str]:
+    """Validate data against schema. Returns list of error strings."""
+    errors = []
+
+    # Try jsonschema if available
+    try:
+        from jsonschema import Draft7Validator
+        validator = Draft7Validator(schema)
+        for err in sorted(validator.iter_errors(data), key=lambda e: list(e.path)):
+            path_str = ".".join(str(p) for p in err.absolute_path) or "(root)"
+            errors.append(f"{path_str}: {err.message}")
+        return errors
+    except ImportError:
+        pass
+
+    # Fallback: manual validation
+    required_top = ["topic", "type", "schema_version", "questions"]
+    for field in required_top:
+        if field not in data:
+            errors.append(f"Missing required field: {field}")
+
+    if data.get("type") not in VALID_TYPES:
+        errors.append(f"Invalid type: {data.get('type')}")
+
+    if data.get("schema_version") != "1.0.0":
+        errors.append(f"schema_version must be '1.0.0', got '{data.get('schema_version')}'")
+
+    for i, q in enumerate(data.get("questions", [])):
+        prefix = f"questions[{i}]"
+        for field in ["id", "type", "difficulty", "tags", "question", "explanation"]:
+            if field not in q:
+                errors.append(f"{prefix}: missing '{field}'")
+        if q.get("type") not in VALID_TYPES:
+            errors.append(f"{prefix}: invalid type '{q.get('type')}'")
+        if "difficulty" in q and not (1 <= q["difficulty"] <= 5):
+            errors.append(f"{prefix}: difficulty must be 1-5")
+        if "id" in q and not ID_RE.match(q["id"]):
+            errors.append(f"{prefix}: id '{q['id']}' doesn't match pattern {{type}}-{{000}}")
+
+    return errors
+
+
+def main():
+    if len(sys.argv) != 2:
+        print(f"Usage: {sys.argv[0]} <json_file | ->", file=sys.stderr)
+        sys.exit(2)
+
+    if not SCHEMA_PATH.exists():
+        print(f"❌ Schema not found: {SCHEMA_PATH}", file=sys.stderr)
+        sys.exit(2)
+
+    schema = load_json(str(SCHEMA_PATH))
+    data = load_json(sys.argv[1])
+    errors = validate(data, schema)
+
+    if errors:
+        print(f"❌ {len(errors)} error(s):")
+        for e in errors:
+            print(f"  • {e}")
+        sys.exit(1)
+    else:
+        print(f"✅ Valid — {len(data.get('questions', []))} question(s)")
+        sys.exit(0)
+
+
+if __name__ == "__main__":
+    main()